Create video using a mix of Audio, Pictures and Music

Looking for someone to do a fun experiment to build an app (preferably cloud based) that allows for someone to record an audio message (1 min or less), upload up to 5 pictures, and select a freeware music song of their choosing. The software would take these 3 inputs (audio, pics and music) and create a video. The app would need to be "intelligent" and be able to stitch together a slide show of the photos (each photo to be displayed an equal amount of time), while the audio message is playing in the "foreground" and the music is playing at a lower volume in the background. For example, if there is a 50 second audio recording and 5 pics uploaded, each pic would appear for 10 seconds. Looking for an MVP of this functionality, with potential enhancements in the future.